计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (19): 1-17.DOI: 10.3778/j.issn.1002-8331.2106-0133

• 热点与综述 • 上一篇    下一篇

零样本学习综述

王泽深,杨云,向鸿鑫,柳青   

  1. 1.云南大学 软件学院,昆明 650504
    2.云南省数据科学与智能计算重点实验室,昆明 650504
  • 出版日期:2021-10-01 发布日期:2021-09-29

Survey on Zero-Shot Learning

WANG Zeshen,YANG Yun,XIANG Hongxin, LIU Qing   

  1. 1.School of Software, Yunnan University, Kunming 650504, China
    2.Yunnan Key Laboratory of Data Science and Intelligent Computing, Kunming 650504, China
  • Online:2021-10-01 Published:2021-09-29

摘要:

尽管自深度学习发展以来,减少大量人工标记样本的需求使得零样本学习取得了不错的进展,以至于已经拥有比较完善的理论体系。但是对于零样本学习应用的研究寥寥无几,如何有效地对应用领域进行梳理是现阶段急需解决的问题。对零样本的理论体系进行介绍,通过一个例子引出零样本学习的定义,继而与广义零样本、监督学习比较,再而列举4个关键问题以及现有的解决方案,给出文本、图像、视频三方面常用的数据集;按照关键技术(属性、嵌入以及生成模型)出现时间顺序,对13个典型模型如何进行零样本学习展开描述,并对优点、缺点、创新点、挑选数据集以及表现进行总结;从词、图像、视频3个维度详细介绍了零样本学习在各个领域的应用;提出了零样本学习过程中出现的挑战并给出了对应的潜在研究方向。

关键词: 零样本学习, 属性, 嵌入空间, 生成模型

Abstract:

Although there have been well developed in zero-shot learning since the development of deep learning, in the aspect of the application, zero-shot learning did not have a good system to order it. This paper overviews theoretical systems of zero-shot learning, typical models, application systems, present challenges and future research directions. Firstly, it introduces the theoretical systems from definition of zero-shot learning, essential problems, and commonly used data sets. Secondly, some typical models of zero-shot learning are described in chronological order. Thirdly, it presents the application systems about of zero-shot learning from the three dimensions, such as words, images and videos. Finally, the paper analyzes the challenges and future research directions in zero-shot learning.

Key words: zero-shot learning, attribute, embedding space, general model